Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Question Classification on TREC (Adversarial Metrics)
Loading...
0.938
Attack Success Rate (ASR)
CacheTrap
0.93552
0.95226
0.969
0.98574
Nov 27, 2025
Attack Success Rate (ASR)
Post-Attack Accuracy (No Trigger)
Updated 4d ago
Evaluation Results
Method
Method
Links
Attack Success Rate (ASR)
Post-Attack Accuracy (No Trigger)
CacheTrap
Model=Mistral-7B, Targ...
2025.11
0.938
-
CacheTrap
Model=Mistral-7B, Targ...
2025.11
0.938
-
CacheTrap
Model=Mistral-7B, Targ...
2025.11
0.968
-
CacheTrap
Model=Mistral-7B, Targ...
2025.11
0.986
0.97
CacheTrap
Model=LLaMA-2-7B, Targ...
2025.11
1
0.97
CacheTrap
Model=LLaMA-2-7B, Targ...
2025.11
1
-
CacheTrap
Model=LLaMA-2-7B, Targ...
2025.11
1
-
CacheTrap
Model=LLaMA-2-7B, Targ...
2025.11
1
-
CacheTrap
Model=LLaMA-2-7B, Targ...
2025.11
1
-
CacheTrap
Model=LLaMA-2-7B, Targ...
2025.11
1
-
CacheTrap
Model=LLaMA-3.1-8B, Ta...
2025.11
1
0.972
CacheTrap
Model=Qwen-2.5-3B, Tar...
2025.11
1
0.966
CacheTrap
Model=DeepSeek-7B, Tar...
2025.11
1
0.948
Feedback
Search any
task
Search any
task